“We transfer the latest research and development advances in data retrieval, analysis, annotation and linking into the media and content industries.”

Company Description

MODUL Technology GmbH is your partner in innovative solutions for media and data collection, annotation and linking, integrating extracted and external knowledge into existing workflows and powering new and extended user interfaces and applications such as: news event or topic detection, social media retrieval and organisation, TV/video enrichment with related information and content.

As a research and innovation spin-off of MODUL University Vienna, the Technology GmbH enables university faculty (as the technology experts) as well as hired researchers and developers to work on near-to-market R&D with a close collaboration with the University itself and support existing and future University spin-offs.

It was founded in 2015 as part of the exploitation plans of the LinkedTV project, in order to continue to coordinate LinkedTV technology development and promote it to industry. It has access to technology experts from throughout the Department of New Media Technology, which conducts cross-disciplinary research on knowledge acquisition, semantic Web annotation, human-computer interaction, data analytics, natural language processing and multimedia description and linking. Its first project collaboration has been to develop solutions for news topic detection and social media retrieval in the InVID project, together with its commercial technology partner webLyzard technology. Since then, we have continued to pursue innovative ideas, and deliver excellence through various national and European projects.

MODUL Technology starts collaboration on analytics platform for TV content

A key concern of TV providers is to exploit the rapidly expanding digital possibilities for networking and publishing quickly and accurately. Now international experts, with significant contributions from Austrian partners MODUL Technology and webLyzard, are beginning to address this problem. The EU project ReTV, funded to the tune of 3.5 million euros, will provide TV providers with a basis for decision-making with a view to adapting existing content to today’s enormous range of digital networks quickly and efficiently.                                                      

Leading media technology experts across Europe have joined forces to enable TV providers to be more agile and responsive to increasing competition from new digital media. Their declared goal is to develop a “trans-vector platform” that provides TV providers with fast, reliable information on who consumes their content as well as when, where and how they do so. It will enable providers to make sound decision-making about future publication of content on those social networks and digital distribution channels as well as where content adaptation is likely to pay off.

Targeted Adaptation

Dr. Lyndon Nixon, CTO of MODUL Technology and assistant professor at the Institute for New Media Technology at MODUL University Vienna comments: “TV providers have to distribute their content through multiple channels such as social media, mobile apps, hybrid TV and digital archives. But compared to print media – which face similar pressures – their content is technically much more complex. Deciding which content should be adapted and in what way is therefore essential for meeting the demands of consumers in a cost-effective manner.”

This is where the ReTV project comes in. The project is coordinated by Vrije Universiteit (VU) Amsterdam, which brings together MODUL Technology and webLyzard as well as other partners from Germany, Switzerland, Greece and the Netherlands. The cooperative project is divided into three clearly defined sections, the results of which will be of enormous value to TV providers. In addition to “aggregation”, i.e. the establishment of a steadily growing directory of TV content, “analysis” and “adaptation” of such content are key elements of the project.

Aggregation & Annotation

More than 10,000 hours of video content and over 50 million documents will be collected and processed from news sources, social media and TV station websites every month. This huge volume of data will then be automatically analysed, and relevant metadata will be appended to every document. Besides “hard” facts, such as links, names and salient visual features, the metadata contain an automatic evaluation of online mood regarding the topics, persons or organizations mentioned in the content. 

Analysis & Adaptation

Professor Arno Scharl, Managing Director of collaborating partner webLyzard, describes how ReTV works: “In the analytical stage, the webLyzard platform is used to capture content trends in social media. This allows intelligent recommendations to be made regarding the adaptation of existing content and the focus for new productions. In this way ReTV will help to optimise advertising strategies, for example by referencing socially relevant topics that are currently being actively discussed by consumers.”

In addition, ReTV will make forecasts about the optimal timing of the release and expected success of original and adapted content. Thanks to the continuous collection and processing of relevant data from a wide range of different sources, the system is also able to learn. If the actual success achieved deviates from predictions, the system will automatically be optimised. In the coming years, ReTV will thus strengthen the competitive situation of European media companies in today’s networked, global market for video content.

First MODUL Technology Project: Welcome, In Video Veritas (InVID)

In January 2016, MODUL Technology GmbH welcomed its first new year 2016 its first self-acquired EU research project: In Video Veritas (InVID)!

InVID sets out to solve a very difficult problem: verifying the truthfulness of video content posted on social networks which claim to show news events. News agencies have to repeatedly deal with fake, manipulated or misrepresented videos being spread online in the aftermath of a news story. To retain their viewers’ trust, they want to be sure of the authenticity of such video before using it in their news reporting. InVID will provide a complete toolset, driven by various innovative technologies, to aid journalists and newsrooms in semi-automatically determining if a video is trustworthy or not.

MODUL Technology GmbH will develop in this project the social media data ingestion pipeline. Data ingestion will be driven by in-time news event detection, since at any one time the InVID platform should only be collecting relevant candidate media for the verification process, i.e. videos being posted which claim to show something related to a current news event. Detected events will be appropriately labelled so that a query mechanism which is regularly updated can retrieve candidate media items from the social platforms. These items, in order to allow for user friendly search and browsing in the applications which use the platform data, will be richly annotated according to their content and structure, with a focus on unambiguous entity detection (e.g. for determining the location claimed to be shown in the video). This pipeline will be integrated as part of the InVID project into the webLyzard Web Intelligence Platform, which forms the core of the InVID platform solution.

MODUL Technology’s news event detection and dynamic social media querying components can help drive any organisations data ingestion needs, e.g. for online media monitoring as part of a Marketing Intelligence approach or for social media browsing as part of an UGC re-use strategy on a Website or a social network channel. Let us work it out for you, contact us now!

Meet the Team

Technology projects are handled by:

Dr. Lyndon Nixon (CTO) brings his more than 15 years of R&D experience to MODUL Technology projects, defining and developing new innovations in media annotation, linking and re-use. His experience includes scientific coordinator for the LinkedTV project and project coordinator of several EU and national projects including MediaMixer.  He is  currently Workpackage Leader in the ReTV project.
Adriana Bassani (Project Manager) ensures a smooth execution of our projects from kick-off through to the successful conclusion. She has experience administrating many EU and national research projects.
Adrian Brasoveanu (Researcher) works in the EPOCH and ReTV projects on the tasks of Named Entity Recognition (NER) and Linking (NEL), developing our innovative entity extraction service RECOGNYZE for multi-lingual and multi-domain semantic annotation.
Pavel Filippov (Researcher) works in the ReTV project on the prediction of content success in different online channels based on past trends using the latest in machine learning techniques.
Jakob Steixner (Researcher) works in the EPOCH and ReTV projects on the extraction of events from external sources, their modelling and maintenance in an Event Knowledge Graph.

What we offer

A FIRST CONSULTANCY ON YOUR DATA AND MEDIA TECHNOLOGY NEEDS IS FREE

  • Consultancy. Find out your media content and metadata requirements and how innovative technologies can help you better manage, re-use and enrich your content!
  • Technology transfer. We develop concepts and demonstrators for you, configure and customise the technology you need and can create a full end-to-end solution for your data and media needs.
  • Knowledge transfer. We can train your staff in new media technology or offer remote support from our experts.

WE CAN DEMONSTRATE AND BUILD DATA AND MEDIA SOLUTIONS AROUND THE FOLLOWING AREAS:

  • Topic detection from data streams.
  • Data retrieval based on real-time changing topics
  • Online and social media content collection
  • Rich media annotation including entity recognition and linking to resources in public Knowledge Graphs (DBPedia, WikiData etc.)
  • Media linking and browsing, including semantic search, faceted navigation and semantic similarity measures

Contact us

Address:

MODUL Technology GmbH

Am Kahlenberg 1

1190 Vienna, Austria

E-mail:

office@modultech.eu

Telephone:

+43-1-3203555-550

Follow us on